{"id":"https://openalex.org/W4406841381","doi":"https://doi.org/10.1109/iccv51701.2025.02582","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","display_name":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406841381","doi":"https://doi.org/10.1109/iccv51701.2025.02582"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.14729","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011993186","display_name":"Xin Zhou","orcid":"https://orcid.org/0000-0002-9661-2540"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhou","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012178361","display_name":"Dingkang Liang","orcid":"https://orcid.org/0000-0003-3035-1373"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingkang Liang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116039274","display_name":"Sifan Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifan Tu","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033302204","display_name":"Xiwu Chen","orcid":"https://orcid.org/0000-0001-5612-9848"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiwu Chen","raw_affiliation_strings":["Mach Drive"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mach Drive","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003453660","display_name":"Yi Ding","orcid":"https://orcid.org/0000-0002-0948-4991"},"institutions":[{"id":"https://openalex.org/I4210109870","display_name":"Vi Technology (United States)","ror":"https://ror.org/016mnbp44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109870"]},{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yikang Ding","raw_affiliation_strings":["MEGVII Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MEGVII Technology","institution_ids":["https://openalex.org/I4210109870","https://openalex.org/I4401726805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025873144","display_name":"Dingyuan Zhang","orcid":"https://orcid.org/0009-0001-5022-8172"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingyuan Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114148705","display_name":"Feiyang Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feiyang Tan","raw_affiliation_strings":["Mach Drive"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mach Drive","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hengshuang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hengshuang Zhao","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0214876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27817","last_page":"27827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5003757476806641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5003757476806641}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.14729","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.14729","pdf_url":"https://arxiv.org/pdf/2501.14729","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.14729","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.14729","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.14729","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.14729","pdf_url":"https://arxiv.org/pdf/2501.14729","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1218466284","display_name":null,"funder_award_id":"62225603,62441615,623B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2549932237","display_name":null,"funder_award_id":"623B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4189157326","display_name":null,"funder_award_id":"62225603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406841381.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Driving":[0,45],"World":[1,46],"Models":[2],"(DWMs)":[3],"have":[4],"become":[5],"essential":[6],"for":[7,110],"autonomous":[8],"driving":[9,36,66],"by":[10,138,147],"enabling":[11,107],"future":[12,57],"scene":[13,21,27,54,58],"prediction.":[14],"However,":[15],"existing":[16],"DWMs":[17],"are":[18],"limited":[19],"to":[20,25,76,124],"generation":[22,113,136],"and":[23,32,56,85,112,121,140,151],"fail":[24],"incorporate":[26,93],"understanding,":[28],"which":[29,92],"involves":[30],"interpreting":[31],"reasoning":[33],"about":[34],"the":[35,103,126],"environment.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"present":[42],"a":[43,62,71],"unified":[44,63],"Model":[47],"named":[48],"HERMES.":[49],"We":[50,87,115],"seamlessly":[51],"integrate":[52],"3D":[53],"understanding":[55,111,142],"evolution":[59],"(generation)":[60],"through":[61],"framework":[64],"in":[65,102],"scenarios.":[67],"Specifically,":[68],"HERMES":[69,131],"leverages":[70],"Bird's-Eye":[72],"View":[73],"(BEV)":[74],"representation":[75],"consolidate":[77],"multi-view":[78],"spatial":[79],"information":[80],"while":[81],"preserving":[82],"geometric":[83],"relationships":[84],"interactions.":[86],"also":[88],"introduce":[89],"world":[90,94],"queries,":[91],"knowledge":[95],"into":[96],"BEV":[97],"features":[98],"via":[99],"causal":[100],"attention":[101],"Large":[104],"Language":[105],"Model,":[106],"contextual":[108],"enrichment":[109],"tasks.":[114],"conduct":[116],"comprehensive":[117],"studies":[118],"on":[119],"nuScenes":[120],"OmniDrive-nuScenes":[122],"datasets":[123],"validate":[125],"effectiveness":[127],"of":[128],"our":[129],"method.":[130],"achieves":[132],"state-of-the-art":[133],"performance,":[134],"reducing":[135],"error":[137],"32.4%":[139],"improving":[141],"metrics":[143],"such":[144],"as":[145],"CIDEr":[146],"8.0%.":[148],"The":[149],"model":[150],"code":[152],"will":[153],"be":[154],"publicly":[155],"released":[156],"at":[157],"https://github.com/LMD0311/HERMES.":[158]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}